All Regions and Campus Levels

You can see a map of the Texas ESC Regions here

library(tidyverse)
library(readxl)
library(plotly)
library(ggpubr)
library(gapminder)
library(kableExtra)
library(summarytools)

# Load TAPR data; rename vars
campus_2019 <- read.csv("docs/TAPR_2019_subset.csv") %>%
  transmute(
    cid = CAMPUS,
    `African American` = CDB00A001219R,
    `Hispanic` = CDH00A001219R,
    `White` = CDW00A001219R,
    aa_total = CDB00A001019D,
    h_total = CDH00A001019D,
    w_total = CDW00A001019D) %>%
  # Filter out schools with no data (~ 10% of campuses)
  filter(!is.na(`African American`) | !is.na(`Hispanic`) | !is.na(`White`))
# Pivot values and descriptive categories
data <- cbind(
  pivot_longer(campus_2019 %>% select(1:4), cols = 2:4, names_to = "Student Group", values_to = "Meets Grade Level (%)"),
  pivot_longer(campus_2019 %>% select(5:7), cols = 1:3, names_to = "group_denom", values_to = "Size of Student Group at School")) %>%
  group_by(cid) %>%
  mutate(
    `Meets Grade Level (%)` = ifelse(`Meets Grade Level (%)` == -1, NA, `Meets Grade Level (%)`), # rate = -1 is masked data and unusable
    `Size of Student Group at School` = ifelse(`Size of Student Group at School` == -1, NA, # denominator = -1 is masked data and unusable
                     `Size of Student Group at School`), 
    `Size of Student Group at School` = ifelse(`Size of Student Group at School` == -3, # denominator = -3 is second smallest group
                     nth(`Size of Student Group at School`, 2, order_by = `Size of Student Group at School`) / 2, 
                     `Size of Student Group at School`), # recover with reasonable proxy of half largest group
    ln_meets_denom = log(`Size of Student Group at School`)) %>% # log will be better for size parameter
  ungroup()

school <- read_excel("docs/school.xlsx")
school <- school %>%
  transmute(
    Campus = `Campus or District`, 
    `Eco. Disadvantaged (%)` = `% Eco Disadvantaged`,
    `Campus Type` = factor(`Entity Type`),
    enrollment_public = Enrollment) %>%
  mutate(
    n = str_split(Campus, " \\|\\|", simplify = TRUE)[,2], # First split on "||"
    nn = str_split(n, " \\(", simplify = TRUE)[,2], # Next splot on " ("
    nnn = str_split(n, " \\(", simplify = TRUE)[,3], # A few have an additional " ("
    cid = as.numeric(gsub("\\D+", "", nn)),
    cid = ifelse(is.na(cid), as.numeric(gsub("\\D+", "", nnn)), cid)) %>%
  select(-starts_with("n"))

codes <- read_csv("docs/school and district.csv")
codes <- codes %>%
  transmute(
    cid = as.numeric(gsub("[^[:alnum:] ]", "", `School Number`)),
    district = as.numeric(gsub("[^[:alnum:] ]", "", `District Number`)),
    county = as.numeric(gsub("[^[:alnum:] ]", "", `County Number`)),
    region = as.numeric(gsub("[^[:alnum:] ]", "", `ESC Region Served`)))

campus <- left_join(school, codes, by = "cid") %>% right_join(data, by = "cid") %>%
  filter(!is.na(Campus))

r <- 1:20
# Blank list for full sample objects
fs <- list()
# Create function to generate 20 plots
plots <- function(data, r, type) {

t <-  ggplot(data = campus %>% filter(`Campus Type` == {{type}} & region == {{r}}), 
         aes(label = `Campus`, label2 = `Size of Student Group at School`, x = `Eco. Disadvantaged (%)`, y = `Meets Grade Level (%)`)) +
  geom_line(alpha = .3, aes(group = cid)) +
  geom_point(alpha = .4, aes(size = `Size of Student Group at School`, color = `Student Group`)) +
  geom_smooth(size = 2, method = loess, color = "black", se = FALSE, aes(group = `Student Group`, weight = ln_meets_denom)) +
  geom_smooth(size = 1.8, method = loess, se = FALSE, aes(color = `Student Group`, weight = ln_meets_denom)) +
  guides(size = FALSE) +
  theme(legend.position = "bottom") +
  xlim(c(0,100)) + ylim(c(0,100)) + 
    ggtitle(paste("Region", {{r}}, {{type}}, "Performance by Race/Ethnicity and Poverty", sep = " "))
  
t[[r]] <- ggplotly(t, tooltip = c("label", "label2", "x", "y"))

#print(t[[r]])
#return(t[[r]])
}

# Stores high school plots for 20 regions in indexed list
gg_hs <- lapply(r, plots, data = campus, type = "High School")

# Stores high school plots for 20 regions in indexed list
gg_jhs <- lapply(r, plots, data = campus, type = "Middle & Jr. High School")

# Stores elementary school plots for 20 regions in indexed list
gg_es <- lapply(r, plots, data = campus, type = "Elementary School")

# Use this function to generate object names, then search and remove extra text.
# for (i in 1:20){
#   print(paste("gg_hs[[", i, "]], ", sep = ""))
#   print(paste("gg_jhs[[", i, "]], ", sep = ""))
#   print(paste("gg_es[[", i, "]], ", sep = ""))
# }


htmltools::tagList(list(gg_hs[[1]], 
gg_jhs[[1]], 
gg_es[[1]], 
gg_hs[[2]], 
gg_jhs[[2]], 
gg_es[[2]], 
gg_hs[[3]], 
gg_jhs[[3]], 
gg_es[[3]], 
gg_hs[[4]], 
gg_jhs[[4]], 
gg_es[[4]], 
gg_hs[[5]], 
gg_jhs[[5]], 
gg_es[[5]], 
gg_hs[[6]], 
gg_jhs[[6]], 
gg_es[[6]], 
gg_hs[[7]], 
gg_jhs[[7]], 
gg_es[[7]], 
gg_hs[[8]], 
gg_jhs[[8]], 
gg_es[[8]], 
gg_hs[[9]], 
gg_jhs[[9]], 
gg_es[[9]], 
gg_hs[[10]], 
gg_jhs[[10]], 
gg_es[[10]], 
gg_hs[[11]], 
gg_jhs[[11]], 
gg_es[[11]], 
gg_hs[[12]], 
gg_jhs[[12]], 
gg_es[[12]], 
gg_hs[[13]], 
gg_jhs[[13]], 
gg_es[[13]], 
gg_hs[[14]], 
gg_jhs[[14]], 
gg_es[[14]], 
gg_hs[[15]], 
gg_jhs[[15]], 
gg_es[[15]], 
gg_hs[[16]], 
gg_jhs[[16]], 
gg_es[[16]], 
gg_hs[[17]], 
gg_jhs[[17]], 
gg_es[[17]], 
gg_hs[[18]], 
gg_jhs[[18]], 
gg_es[[18]], 
gg_hs[[19]], 
gg_jhs[[19]], 
gg_es[[19]], 
gg_hs[[20]], 
gg_jhs[[20]], 
gg_es[[20]]))